Determining autonomous vehicle technology performance for insurance pricing and offering
Methods and systems for evaluating the effectiveness of autonomous operation features of autonomous vehicles are provided. According to certain aspects, information regarding autonomous operation features associated with a vehicle may be determined and used to determine a likelihood of an accident for the vehicle. Determining the likelihood of an accident may include determining risk factors for the features related to the ability of the features to make control decisions that successfully avoid accidents. This may include reference to test data or actual loss data associated with the features, as well as usage data regarding expected use of the features during vehicle operation. Effectiveness of the features may be evaluated relative to location or operating conditions, as well as types and severity of accidents. The determined effectiveness of the features of a vehicle may further be used to determine or adjust aspects of an insurance policy associated with the vehicle.
1. A computer-implemented method of evaluating effectiveness of an autonomous or semi-autonomous technology of a vehicle in controlling the vehicle, the method comprising:
generating, by one or more test units configured to simultaneously test a plurality of autonomous or semi-autonomous technologies, test data indicating a performance of the plurality of autonomous or semi-autonomous technologies and including test control decisions of a plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology generated in response to test sensor data that simulates sensor data for a test vehicle operating under a plurality of operating conditions in a virtual test environment;
monitoring and recording, by an on-board computer of the vehicle during vehicle operation, the test data regarding usage and operation of the autonomous or semi-autonomous technology associated with the vehicle in controlling the vehicle during vehicle operation under a plurality of observed operating conditions, including an indication of a current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology;
receiving, at one or more processors, baseline data regarding risk levels associated with vehicle operation by the autonomous or semi-autonomous technology, including test data associated with the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology and an additional version of the plurality of versions of the autonomous or semi-autonomous technology;
comparing, by one or more processors, the monitored and recorded test data to the baseline data to determine a quality metric indicating an effectiveness of the autonomous or semi-autonomous technology based upon a quality of control decisions of the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology implemented by the vehicle in avoiding or mitigating an effect of vehicle collisions relative to a quality of control decisions of the additional version of the plurality of versions of the autonomous or semi-autonomous technology;
determining, by one or more processors, an accident risk associated with the vehicle based upon the determined quality metric;
determining, by one or more processors, an insurance policy based at least in part upon the determined accident risk associated with the vehicle; and
causing, by one or more processors, one or more of the following actions to be performed based upon the determined insurance policy: adjusting the insurance policy, determining a coverage level associated with the insurance policy, presenting information regarding the insurance policy to a reviewer via a display of a reviewer computing device to verify the determined insurance policy, or presenting information regarding the insurance policy for the vehicle to a customer for review,
wherein the autonomous or semi-autonomous technology performs at least one of the following functions: steering; accelerating; braking; monitoring blind spots; presenting a collision warning; adaptive cruise control; parking; driver alertness monitoring; driver responsiveness monitoring; pedestrian detection; artificial intelligence; a back-up system; a navigation system; a positioning system; a security system; an anti-hacking measure; a theft prevention system; or remote vehicle location determination.
2. The computer-implemented method of claim 1 , wherein the baseline data further includes information stored in one or more databases regarding actual accident data involving vehicles equipped with the autonomous or semi-autonomous technology.
3. The computer-implemented method of claim 1 , wherein the accident risk is determined, at least in part, based upon an extent of control exerted by the autonomous or semi-autonomous technology, rather than a human vehicle operator.
4. The computer-implemented method of claim 1 , wherein the accident risk is determined, at least in part, based upon a quality of an ability of the vehicle to use communication information received by an autonomous communication feature from another vehicle or from an infrastructure component to make control decisions for the vehicle.
5. The computer-implemented method of claim 1 , wherein information regarding the autonomous or semi-autonomous technology associated with the vehicle is transmitted by a network to a server associated with at least one of an insurance provider or a third party for analysis.
6. The computer-implemented method of claim 1 , the method further comprising:
determining, by one or more processors, one or more of the following actions to be taken based upon a monitored level of usage of the autonomous or semi-autonomous technology during vehicle operation: (a) providing feedback to at least one of a vehicle operator or an insurance provider, or (b) adjusting at least one of a premium or cost associated with the insurance policy.
7. A computer system for evaluating effectiveness of an autonomous or semi-autonomous technology of a vehicle in controlling the vehicle, comprising:
one or more processors;
one or more communication modules adapted to communicate data;
one or more test units configured to simultaneously test a plurality of autonomous or semi-autonomous technologies, including the autonomous or semi-autonomous technology, by generating test data that indicates a performance of the plurality of autonomous or semi-autonomous technologies and that includes test control decisions of a plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology generated in response to test sensor data that simulates sensor data for a test vehicle operating under a plurality of operating conditions in a virtual test environment; and
a program memory coupled to the one or more processors and storing executable instructions that when executed by the one or more processors cause the computer system to:
receive the test data regarding usage and operation of the autonomous or semi-autonomous technology associated with the vehicle in controlling the vehicle under a plurality of observed operating conditions, including an indication of a current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology, wherein the test data is monitored and recorded by an on-board computer of the vehicle during vehicle operation;
receive baseline data regarding risk levels associated with vehicle operation by the autonomous or semi-autonomous technology, including test data associated with the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology and an additional version of the plurality of versions of the autonomous or semi-autonomous technology;
compare the monitored and received test data to the baseline data to determine a quality metric indicating an effectiveness of the autonomous or semi-autonomous technology based upon a quality of control decisions of the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous technology implemented by the vehicle in avoiding or mitigating an effect of vehicle collisions relative to a quality of control decisions of the additional version of the plurality of versions of the autonomous or semi-autonomous technology;
determine an accident risk associated with the vehicle based upon the determined quality metric;
determine an insurance policy based at least in part upon the determined accident risk associated with the vehicle; and
cause one or more of the following actions to be performed based upon the determined insurance policy: adjusting the insurance policy, determining a coverage level associated with the insurance policy, presenting information regarding the insurance policy to a reviewer via a display of a reviewer computing device to verify the determined insurance policy, or presenting information regarding the insurance policy for the vehicle to a customer for review,
wherein the autonomous or semi-autonomous technology performs at least one of the following functions: steering; accelerating; braking; monitoring blind spots; presenting a collision warning; adaptive cruise control; parking; driver alertness monitoring; driver responsiveness monitoring; pedestrian detection; artificial intelligence; a back-up system; a navigation system; a positioning system; a security system; an anti-hacking measure; a theft prevention system; or remote vehicle location determination.
8. A computer-implemented method of evaluating effectiveness of an autonomous or semi-autonomous functionality of a vehicle in controlling the vehicle, the method comprising:
generating, by one or more test units configured to simultaneously test a plurality of autonomous or semi-autonomous vehicle functionalities, test data indicating a performance of the plurality of autonomous or semi-autonomous functionalities and including test control decisions of a plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality generated in response to test sensor data that simulates sensor data for a test vehicle operating under a plurality of operating conditions in a virtual test environment;
monitoring and recording, by an on-board computer of the vehicle during vehicle operation, the test data regarding operation of the autonomous or semi-autonomous functionality in controlling the vehicle during vehicle operation under a plurality of observed operating conditions, including an indication of a current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality;
receiving, at one or more processors, baseline data regarding risk levels associated with vehicle operation by the autonomous or semi-autonomous functionality, including test data associated with the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality and an additional version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality;
determining, by one or more processors, a relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and a likelihood of an accident involving the vehicle based upon the monitored and recorded test data and the baseline data, wherein the relationship is based at least in part upon an additional relationship between the additional version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle;
determining, by one or more processors, an insurance policy for the vehicle based at least in part upon the determined relationship, wherein determining the insurance policy includes determining one or more of the following: an insurance premium, a discount, or a reward; and
causing, by one or more processors, one or more of the following actions to be performed based upon the determined insurance policy: adjusting the insurance policy, determining a coverage level associated with the insurance policy, presenting information regarding the insurance policy to a reviewer via a display of a reviewer computing device to verify the determined insurance policy, or presenting information regarding the insurance policy for the vehicle to a customer for review,
wherein the autonomous or semi-autonomous functionality performs at least one of the following functions: steering; accelerating; braking; monitoring blind spots; presenting a collision warning; adaptive cruise control; parking; driver alertness monitoring; driver responsiveness monitoring; pedestrian detection; artificial intelligence; a back-up system; a navigation system; a positioning system; a security system; an anti-hacking measure; a theft prevention system; or remote vehicle location determination.
9. The computer-implemented method of claim 8 , wherein determining the insurance policy further includes determining a risk factor associated with the relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle and determining the insurance policy based at least in part upon the risk factor.
10. The computer-implemented method of claim 8 , wherein determining the relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle includes receiving, by one or more processors, information regarding the likelihood of an accident associated with the current version of the plurality of versions of the autonomous or semi-autonomous functionality stored in a risk assessment database including actual accident information involving vehicles having the autonomous or semi-autonomous functionality.
11. The computer-implemented method of claim 10 , wherein the risk assessment database includes information regarding one or more of the following: types of accidents, types of roads, types of vehicles, or weather conditions.
12. The computer-implemented method of claim 8 , wherein the autonomous or semi-autonomous functionality involves at least one of a vehicle self-braking functionality or a vehicle self-steering functionality.
13. The computer-implemented method of claim 8 , wherein presenting the information regarding the insurance policy for the vehicle to the customer includes presenting, by a display screen, a cost of automobile insurance coverage.
14. The computer-implemented method of claim 8 , the method further comprising:
monitoring, by one or more processors, a usage level of the autonomous or semi-autonomous functionality; and
adjusting, by one or more processors, the insurance policy based at least in part upon the usage level of the autonomous or semi-autonomous functionality.
15. The computer-implemented method of claim 8 , wherein the relationship is further determined based upon additional data related to vehicle accidents involving vehicles having the autonomous or semi-autonomous functionality.
16. A tangible, non-transitory computer-readable medium storing instructions for evaluating effectiveness of an autonomous or semi-autonomous functionality of a vehicle in controlling the vehicle that, when executed by at least one processor of a computer system, cause the computer system to:
generate test data using one or more test units configured to simultaneously test a plurality of autonomous or semi-autonomous vehicle functionalities, wherein the test data indicates a performance of the plurality of autonomous or semi-autonomous functionalities and includes test control decisions of a plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality generated in response to test sensor data that simulates sensor data for a test vehicle operating under a plurality of operating conditions in a virtual test environment;
receive the test data regarding operation of the autonomous or semi-autonomous functionality in controlling the vehicle under a plurality of observed operating conditions, including an indication of a current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality, wherein the test data is monitored and recorded by an on-board computer of the vehicle during vehicle operation;
receive baseline data regarding risk levels associated with vehicle operation by the autonomous or semi-autonomous functionality, including test data associated with the current version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality and an additional version of the plurality of versions of computer-readable instructions of the autonomous or semi-autonomous functionality;
determine a relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and a likelihood of an accident involving the vehicle based upon the monitored and received test data and the baseline data, wherein the relationship is based at least in part upon an additional relationship between the additional version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle;
determine an insurance policy for the vehicle based at least in part upon the determined relationship, wherein determining the insurance policy includes determining one or more of the following: an insurance premium, a discount, or a reward; and
cause one or more of the following actions to be performed based upon the determined insurance policy: adjusting the insurance policy, determining a coverage level associated with the insurance policy, presenting information regarding the insurance policy to a reviewer via a display of a reviewer computing device to verify the determined insurance policy, or presenting information regarding the insurance policy for the vehicle to a customer for review,
wherein the autonomous or semi-autonomous functionality performs at least one of the following functions: steering; accelerating; braking; monitoring blind spots; presenting a collision warning; adaptive cruise control; parking; driver alertness monitoring; driver responsiveness monitoring; pedestrian detection; artificial intelligence; a back-up system; a navigation system; a positioning system; a security system; an anti-hacking measure; a theft prevention system; or remote vehicle location determination.
17. The tangible, non-transitory computer-readable medium of claim 16 , wherein:
determining the insurance policy further includes determining a risk factor associated with the relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle and determining the insurance policy based at least in part upon the risk factor; and
determining the relationship between the current version of the plurality of versions of the autonomous or semi-autonomous functionality and the likelihood of an accident involving the vehicle includes receiving, by one or more processors, information regarding the likelihood of an accident associated with the autonomous or semi-autonomous functionality stored in a risk assessment database including at least one of (a) actual accident information involving vehicles having the autonomous or semi-autonomous functionality, or (b) test result data associated with vehicles having the autonomous or semi-autonomous functionality.